dev

Enhance a plan with parallel research agents for each section, adding depth, best practices, and implementation details

Create a new blog post following content patterns

Create a new React or Astro component

Create a new application page following project conventions

Analyzes the current project and generates or updates the `CLAUDE.md` file with comprehensive context from installed marketplace plugins. Works with **any project type** (JavaScript, Python, Rust, Go, PHP, Ruby, Java, etc.).

Generate a skill from Context7 MCP documentation response

Run Playwright tests and verify visual changes

Manage file-based todos with create, list, update, and dependency tracking

Document solved problems as categorized knowledge with YAML frontmatter for fast lookup and future reference

Transform feature descriptions into well-structured project plans following conventions, with parallel research agents for each section

Perform exhaustive code reviews using multi-agent parallel analysis with ultra-thinking and worktrees

Execute structured work with quality gates and agent scrutiny. For implementing features from plans or todos with automatic quality checkpoints.

Use this agent when researching external best practices, documentation, and examples for any technology, framework, or development practice. Specializes in gathering information from official documentation, community standards, and well-regarded open source projects. Triggers on requests like "research best practices", "find examples of", "how should I implement".

Use this agent when needing to gather comprehensive documentation and best practices for specific frameworks, libraries, or dependencies in a project. Specializes in fetching official documentation, exploring source code, identifying version-specific constraints, and understanding implementation patterns. Triggers on requests like "lookup framework docs", "how do I use", "find documentation for".

Use this agent when understanding the historical context and evolution of code changes, tracing the origins of specific code patterns, identifying key contributors and their expertise areas, or analyzing patterns in commit history. Triggers on requests like "git history analysis", "why was this written", "who owns this code".

Use this agent when conducting thorough research on a repository's structure, documentation, and patterns. Specializes in analyzing architecture files, examining GitHub issues, reviewing contribution guidelines, and searching for implementation patterns. Triggers on requests like "analyze repository", "research codebase structure", "find patterns in repo".

Use this agent when reviewing code changes to ensure features are agent-native - any action a user can take, an agent can also take, and anything a user can see, an agent can see. Triggers on requests like "agent-native review", "AI accessibility check".

Use this agent when analyzing code changes from an architectural perspective, evaluating system design decisions, or ensuring changes align with established architectural patterns. Triggers on requests like "architecture review", "design evaluation", "system architecture analysis".

Use this agent when reviewing code changes to ensure they are as simple and minimal as possible. Applies when implementation is complete but before finalizing changes. Triggers on requests like "check for over-engineering", "review for simplicity", "YAGNI review".

Use this agent when reviewing database migrations, data models, or any code that manipulates persistent data. Specializes in validating referential integrity, transaction boundaries, and data validation rules. Triggers on requests like "data integrity review", "database safety check".

Use this agent when reviewing database migrations, schema changes, or data transformations. Specializes in validating ID mappings, checking for swapped values, and verifying rollback safety. Triggers on requests like "migration review", "schema change validation".

Use this agent when creating deployment verification checklists for PRs that touch production data, migrations, or risky behavior changes. Generates Go/No-Go decision criteria with SQL verification queries and rollback procedures. Triggers on requests like "deployment checklist", "verify deployment", "pre-deploy checks".

Use this agent when analyzing code for design patterns, anti-patterns, naming conventions, and code consistency. Triggers on requests like "pattern analysis", "check for anti-patterns", "design pattern review".

Use this agent when analyzing code for performance issues, optimization opportunities, or scalability concerns. Triggers on requests like "performance review", "check for bottlenecks", "scalability analysis".

Use this agent when performing security audits, vulnerability assessments, or security reviews of code. Triggers on requests like "security review", "check for vulnerabilities", "OWASP compliance check".

Automatically generates skills from Context7 MCP documentation responses

This skill should be used when managing the file-based todo tracking system in the todos/ directory. Triggers on requests like "create a todo", "update todo status", "manage todos", "check todo dependencies".

Manages git operations including commits, pull requests, merge requests, and branching. Use when creating commits, handling git conflicts, managing branches, or reviewing git history. Enforces clean commit messages without author attribution.

Manage plans and context documents with automatic indexing

This skill should be used when classifying issues, findings, or code review problems with severity levels. Triggers on requests like "classify severity", "what is P1/P2/P3", "determine issue priority".

Orchestrates complete skill lifecycle from creation to optimization. Use for comprehensive skill development, reviewing skills, or managing skill quality.

Generates Claude Code skills from user descriptions. Use when creating new skills, converting documentation to skills, or scaffolding skill structure.

Refactors Claude Code skills to reduce token usage 80-95% using Progressive Disclosure Architecture (PDA). Splits monolithic skills into orchestrator + reference files, extracts scripts, creates reference/ directories. Use when optimizing skills, improving skill efficiency, refactoring large/bloated skills, reducing token costs, applying PDA, modularizing skills, breaking down skills, or converting encyclopedia-style skills to orchestrator pattern.

Reviews Claude Code skills for quality, best practices, and improvement opportunities. Use when evaluating skills, checking for PDA compliance, or identifying optimization opportunities.

3 hooks across 3 events